← Back to Skills Marketplace
tangweigang-jpg

Py Vollib Options Pricing

by Tang Weigang · GitHub ↗ · v0.3.3 · MIT-0
cross-platform ⚠ suspicious
113
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install py-vollib-options-pricing
Description
使用 BSM 和 Black 模型对欧式期权进行定价和 Greeks 计算,支持连续股息收益率调整。
Usage Guidance
This skill is internally inconsistent: it says it's an options-pricing helper but its instructions expect a full quant/backtest environment (zvt), Python 3.12+, access to ZVT_HOME (~/.zvt), and will run Python commands that may create files. Before installing or invoking: (1) Confirm the authoritative source and license (homepage/source unknown and LICENSE is proprietary). (2) Ask the publisher which exact dependencies are required and why the skill must run zvt commands and touch ~/.zvt. (3) If you must try it, run it in an isolated environment (temporary VM or container) with no sensitive credentials and with ZVT_HOME pointed to a disposable directory. (4) If you don't use ZVT or have no need for backtest/trading execution, prefer a narrower tool that only exposes option pricing math. (5) Consider requesting a version that documents installs and required env vars in the registry metadata rather than only in SKILL.md.
Capability Analysis
Type: OpenClaw Skill Name: py-vollib-options-pricing Version: 0.3.3 The skill bundle provides a highly structured framework for European option pricing and Greeks calculation using Black-Scholes-Merton (BSM) and Black models. It utilizes an extensive set of domain-specific 'semantic locks' and 'fatal constraints' (primarily in seed.yaml and SKILL.md) to enforce rigorous financial modeling standards, such as dividend yield adjustments and industry-standard Greek scaling. While the bundle contains complex meta-instructions and behavior-shaping prompts for the AI agent, these are clearly aligned with ensuring the accuracy and physical plausibility of generated quantitative finance code. No indicators of data exfiltration, malicious execution, or unauthorized persistence were found.
Capability Tags
crypto
Capability Assessment
Purpose & Capability
Name/description focus on BSM/Black option pricing and Greeks, but the SKILL.md and reference files describe a full quant pipeline (data_collection -> trading_execution -> visualization), backtest triggers, Sphinx doc automation, and integration with ZVT. The registry metadata/requirements declared no binaries or env vars, yet SKILL.md explicitly requires Python 3.12+ and 'uv' package manager and references zvt/ZVT_HOME. These extra capabilities (backtesting/trading execution, recorder preconditions) are not justified by the narrow name/description.
Instruction Scope
SKILL.md instructs the agent to run precondition Python commands (import zvt, run recorders), check and possibly write to ZVT_HOME (~/.zvt), and follow semantic locks that affect trading behavior (fatal halts). It also instructs re-reading seed.yaml on every behavioral decision. Those instructions access filesystem and environment variables and perform operational checks beyond simple option pricing math; they could cause the agent to run commands that alter local state or require credentials/configuration not declared.
Install Mechanism
There is no install spec (instruction-only), which reduces the risk of arbitrary downloads. However, SKILL.md claims a runtime dependency on Python 3.12+ and the 'uv' package manager but provides no automated installation or verification steps in the registry metadata. That mismatch may cause the agent to attempt ad-hoc installs or fail preconditions.
Credentials
Registry declares no required env vars or credentials, yet the instructions reference ZVT_HOME and run Python snippets that read/write that path and expect zvt to be installed. The skill may access or create files under ~/.zvt and execute recorder commands. The absence of declared env requirements (and no explanation of why filesystem access is needed) is disproportionate to the stated options-pricing purpose.
Persistence & Privilege
The skill does not request 'always: true' and does not declare modifying other skills. However the seed.yaml execution protocol instructs agents to re-read seed.yaml, run preconditions, and use workspace paths (scripts/, skills/, .trace/). Preconditions can create or touch files under ZVT_HOME. While not high privilege by itself, these behaviors grant the skill the ability to change local state and should be considered when granting runtime permissions.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install py-vollib-options-pricing
  3. After installation, invoke the skill by name or use /py-vollib-options-pricing
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.3.3
v0.3.3: bilingual metadata injected. H1 shows 期权 BSM 定价; tagline replaced with skill-specific Chinese hook; tags upgraded to Level 1-4.
v0.3.1
Remove install.sh — knowledge-only bundle. Host AI consumes directly from URL; no user-side installation needed. Fixes ClawHub suspicious flag.
v0.3.0
Doramagic crystal portfolio v0.3.0. Full 5-layer bp-009 standard. github.com/tangweigang-jpg/doramagic-skills
Metadata
Slug py-vollib-options-pricing
Version 0.3.3
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 3
Frequently Asked Questions

What is Py Vollib Options Pricing?

使用 BSM 和 Black 模型对欧式期权进行定价和 Greeks 计算,支持连续股息收益率调整。 It is an AI Agent Skill for Claude Code / OpenClaw, with 113 downloads so far.

How do I install Py Vollib Options Pricing?

Run "/install py-vollib-options-pricing" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Py Vollib Options Pricing free?

Yes, Py Vollib Options Pricing is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Py Vollib Options Pricing support?

Py Vollib Options Pricing is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Py Vollib Options Pricing?

It is built and maintained by Tang Weigang (@tangweigang-jpg); the current version is v0.3.3.

💬 Comments